oxy-app-builder

oxy-app-builder is a cursor rule for coding agents from oxy-hq/skills. It costs 0 tokens per session (2,418 once invoked), scanned A, original, MIT.

A builder for Oxy data apps: YAML-defined dashboards that run data tasks and show their results as tables or other displays.

In plain words
What is it for?
Use it to create or edit app files containing database tasks and displays for interactive dashboards and reports.
Why use it?
It gives the app a consistent structure for connecting queries to what users see, reducing confusion between declarative dashboards and custom React/Vite applications.

Cursor rule

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/oxy-hq/skills/oxy-app-builder
Clone the repo
git clone --depth 1 https://github.com/oxy-hq/skills

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for oxy-app-builder

README.md
[![agentmods](https://agentmods.dev/badge/rules/oxy-hq/skills/oxy-app-builder.svg)](https://agentmods.dev/rules/oxy-hq/skills/oxy-app-builder)
Your own site
<a href="https://agentmods.dev/rules/oxy-hq/skills/oxy-app-builder"><img src="https://agentmods.dev/badge/rules/oxy-hq/skills/oxy-app-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,418 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02418
Opus 5 $0.00000 $0.01209
Sonnet 5 $0.00000 $0.00484
Haiku 4.5 $0.00000 $0.00242

Measured 3d ago against content hash 98b48b50658a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oxy-app-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

cursor/rules/oxy-app-builder.mdc · 412 lines

How it starts

The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oxy App Builder

Build Oxy data apps - interactive dashboards that combine data tasks with visualizations. Apps are defined in *.app.yml files.

The mental model: Task -> Output -> Display

Two app models — don't confuse them. This rule builds the declarative *.app.yml app (tasks + displays, rendered by oxy serve --enterprise). The other model is a custom-code (React/Vite) app deployed with oxy publish and identified by an oxy-app.json manifest at the app root. oxy-app.json is the deploy manifest for that path, not an alternative to *.app.yml. See the oxy-app-builder SKILL.md → "Deploying custom-code apps (oxy-app.json)".

App YAML Structure

name: app_name                # snake_case identifier
description: |                # Multi-line description
  What this app does...

# Required: Array of tasks (min 1)
tasks:
  - name: task_name           # Unique, snake_case
    type: execute_sql         # Task type
    database: clickhouse      # Database to query
    sql_query: |              # Inline SQL
      SELECT * FROM table

# Required: Array of displays (min 1)
display:
  - type: table
    title: "Results"
    data: task_name           # Reference task by name

Task Types

1. execute_sql - Direct SQL Execution

- name: sales_by_region
  type: execute_sql
  database: clickhouse        # or: postgres, bigquery, local (DuckDB)
  sql_query: |
    SELECT region, SUM(amount) as total
    FROM sales
    GROUP BY region

Or reference a SQL file:

- name: sales_report
  type: execute_sql
  database: clickhouse
  sql_file: queries/sales_report.sql

2. workflow - Invoke Sub-Workflow

- name: data_prep
  type: workflow
  src: workflows/data_prep.workflow.yml
  variables:
    start_date: "2024-01-01"
    min_threshold: 100

Reference workflow task outputs: workflow_name.inner_task_name

3. semantic_query - Query Semantic Layer

- name: revenue_by_month
  type: semantic_query
  topic: sales_mrr
  dimensions:
    - sales.month
  measures:
    - sales.total_revenue
    - sales.order_count
  filters:
    - field: sales.year
      op: eq
      value: 2024
  orders:
    - field: sales.month
      direction: asc

Read the full file on GitHub · 412 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 412 lines · 0 tokens per session scan A 98b48b50658a

Subscribe to this mod's changes

oxy-app-builder is a cursor rule published in the GitHub repository oxy-hq/skills (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,418 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.